Hugging Face's logo

qminh369
/
token-classification-llmlingua2-xlm-roberta-bctn-852_sample-5_epoch_best_data

Token Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
qminh369 commited on
Commit
169e8c8
•
1 Parent(s): 915b5c7

End of training

Browse files
Files changed (24) hide show
  1. .gitattributes +1 -0
  2. README.md +63 -0
  3. config.json +28 -0
  4. model.safetensors +3 -0
  5. runs/Apr16_10-19-19_aies-gpu-a30/events.out.tfevents.1713237581.aies-gpu-a30.708128.0 +3 -0
  6. runs/Apr16_10-19-59_aies-gpu-a30/events.out.tfevents.1713237600.aies-gpu-a30.708128.1 +3 -0
  7. runs/Apr16_10-21-02_aies-gpu-a30/events.out.tfevents.1713237663.aies-gpu-a30.708128.2 +3 -0
  8. runs/Apr16_10-21-34_aies-gpu-a30/events.out.tfevents.1713237695.aies-gpu-a30.2671439.0 +3 -0
  9. runs/Apr16_10-23-06_aies-gpu-a30/events.out.tfevents.1713237786.aies-gpu-a30.2671439.1 +3 -0
  10. runs/Apr16_10-42-21_aies-gpu-a30/events.out.tfevents.1713238942.aies-gpu-a30.2673526.0 +3 -0
  11. runs/Apr16_10-49-45_aies-gpu-a30/events.out.tfevents.1713239386.aies-gpu-a30.2697251.0 +3 -0
  12. runs/Apr16_10-53-00_aies-gpu-a30/events.out.tfevents.1713239580.aies-gpu-a30.2700178.0 +3 -0
  13. runs/Apr16_10-53-21_aies-gpu-a30/events.out.tfevents.1713239602.aies-gpu-a30.2700178.1 +3 -0
  14. runs/Apr16_14-51-17_aies-gpu-a30/events.out.tfevents.1713253893.aies-gpu-a30.2921328.0 +3 -0
  15. runs/Apr16_15-03-05_aies-gpu-a30/events.out.tfevents.1713254585.aies-gpu-a30.2923997.0 +3 -0
  16. runs/Apr16_15-06-18_aies-gpu-a30/events.out.tfevents.1713254779.aies-gpu-a30.2937732.0 +3 -0
  17. runs/Apr16_15-21-04_aies-gpu-a30/events.out.tfevents.1713255665.aies-gpu-a30.2952261.0 +3 -0
  18. runs/Apr16_15-55-30_aies-gpu-a30/events.out.tfevents.1713257733.aies-gpu-a30.2962208.0 +3 -0
  19. runs/Apr16_15-55-30_aies-gpu-a30/events.out.tfevents.1713258724.aies-gpu-a30.2962208.1 +3 -0
  20. sentencepiece.bpe.model +3 -0
  21. special_tokens_map.json +15 -0
  22. tokenizer.json +3 -0
  23. tokenizer_config.json +54 -0
  24. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: FacebookAI/xlm-roberta-large
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: token-classification-llmlingua2-xlm-roberta-bctn-852_sample-5_epoch_best_data
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # token-classification-llmlingua2-xlm-roberta-bctn-852_sample-5_epoch_best_data
15
+
16
+ This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.2243
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 1e-05
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 1
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 16
42
+ - total_train_batch_size: 16
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 5
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | No log | 0.99 | 42 | 0.2380 |
52
+ | No log | 2.0 | 85 | 0.2288 |
53
+ | No log | 2.98 | 127 | 0.2243 |
54
+ | No log | 3.99 | 170 | 0.2246 |
55
+ | No log | 4.93 | 210 | 0.2251 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.39.0.dev0
61
+ - Pytorch 2.2.1+cu118
62
+ - Datasets 2.18.0
63
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.39.0.dev0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae3dc7a8400de75e556d06a6e5483031ee70e709071f02c49943beb15765d83
3
+ size 2235420048
runs/Apr16_10-19-19_aies-gpu-a30/events.out.tfevents.1713237581.aies-gpu-a30.708128.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ac9e7bc6083d3283175ab6fe961ec0a8122a234abdc47dd85ca690f72ab6f02
3
+ size 4988
runs/Apr16_10-19-59_aies-gpu-a30/events.out.tfevents.1713237600.aies-gpu-a30.708128.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695b2e91e22350f3a2bf78614416d79f36037d75fbf0148079c300516fa6819e
3
+ size 4988
runs/Apr16_10-21-02_aies-gpu-a30/events.out.tfevents.1713237663.aies-gpu-a30.708128.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b51f532648d3cb75a91677d34eab8cd368d172083245a83eea2eb9187025e1
3
+ size 4988
runs/Apr16_10-21-34_aies-gpu-a30/events.out.tfevents.1713237695.aies-gpu-a30.2671439.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:debdaaffb53addd48e962aacd1e0b4cef8b7f628f07877758215a451419325b3
3
+ size 4988
runs/Apr16_10-23-06_aies-gpu-a30/events.out.tfevents.1713237786.aies-gpu-a30.2671439.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bcdf08b63ae33dc696d2a6404e2a4016006359495c67326b7de06c806c40310
3
+ size 4988
runs/Apr16_10-42-21_aies-gpu-a30/events.out.tfevents.1713238942.aies-gpu-a30.2673526.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a3ef8ab3fee2034aa4a93f6cdff09eaf9d7b81cf8597a7da8c39360248126d0
3
+ size 4988
runs/Apr16_10-49-45_aies-gpu-a30/events.out.tfevents.1713239386.aies-gpu-a30.2697251.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6aae64656004321be2c31c07aa7273a0586158eb3d06aa405d011ec952e5644
3
+ size 4988
runs/Apr16_10-53-00_aies-gpu-a30/events.out.tfevents.1713239580.aies-gpu-a30.2700178.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c51e1ca500fdc02c1a37cedcef96bd934cc0152976451dccb2d90480cd90b109
3
+ size 4988
runs/Apr16_10-53-21_aies-gpu-a30/events.out.tfevents.1713239602.aies-gpu-a30.2700178.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4353fb09cee9911d2c413f515b16297876deb1f45d462a076d338ba3a7b01fb
3
+ size 4988
runs/Apr16_14-51-17_aies-gpu-a30/events.out.tfevents.1713253893.aies-gpu-a30.2921328.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d15b7d2e0021c11fe5c9feea5ce46b77714beb0651dd0998604a42f8778e58a1
3
+ size 4988
runs/Apr16_15-03-05_aies-gpu-a30/events.out.tfevents.1713254585.aies-gpu-a30.2923997.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42df220c9f4c3a98bf3a8e3583b814ec450d743c4a3dbacf353a199ad3dd435a
3
+ size 4988
runs/Apr16_15-06-18_aies-gpu-a30/events.out.tfevents.1713254779.aies-gpu-a30.2937732.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3849c2309b07fd9ad354d299f57491accfc36216100a30d85885b45e08c0318c
3
+ size 4988
runs/Apr16_15-21-04_aies-gpu-a30/events.out.tfevents.1713255665.aies-gpu-a30.2952261.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70958566919f84f58e9b7a71cc1b7021ff7eb38579922808872a8724ef0c5580
3
+ size 4988
runs/Apr16_15-55-30_aies-gpu-a30/events.out.tfevents.1713257733.aies-gpu-a30.2962208.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6439ce56376f85de6f965d892f7acce94c69878b5bca8ac0c5cd897bbfd47cb
3
+ size 6682
runs/Apr16_15-55-30_aies-gpu-a30/events.out.tfevents.1713258724.aies-gpu-a30.2962208.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a6f1d6de542297037fc1762066507e0119ceecc70de4404310892ace30184d
3
+ size 359
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
3
+ size 17082756
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48996ebd3ad26d794e09814318a8b1e110a5428bef8856d02bc0427c047ddbe9
3
+ size 5176